用可解释的深度学习模型，精准识别儿童肺炎胸片。
XAI-Guided Analysis of Residual Networks for Interpretable Pneumonia Detection in Paediatric Chest X-rays
- 结合贝叶斯梯度加权显著图，量化视觉解释的不确定性。
- 在儿童胸片上达到95.94%准确率，AUC-ROC达98.91%。
- 为临床部署提供高精度且可解释的AI诊断方案。
肺炎仍是全球儿童死亡的主要原因之一，亟需快速准确的诊断工具。本文提出一种基于残差网络（ResNets）的可解释深度学习模型，用于自动诊断儿童胸片中的肺炎。通过引入贝叶斯梯度加权类激活映射（BayesGrad-CAM），量化模型决策过程中的视觉解释不确定性，提供可信的空间定位依据。基于大规模儿童胸片数据集训练的ResNet-50模型，在分类任务中取得95.94%的准确率、98.91%的AUC-ROC值以及0.913的Cohen's Kappa系数，并生成具有临床意义的可视化解释。研究证明，高性能与可解释性在临床AI应用中不仅可兼得，而且至关重要。
原文摘要 · Abstract (English)
Pneumonia remains one of the leading causes of death among children worldwide, underscoring a critical need for fast and accurate diagnostic tools. In this paper, we propose an interpretable deep learning model on Residual Networks (ResNets) for automatically diagnosing paediatric pneumonia on chest X-rays. We enhance interpretability through Bayesian Gradient-weighted Class Activation Mapping (BayesGrad-CAM), which quantifies uncertainty in visual explanations, and which offers spatial locations accountable for the decision-making process of the model. Our ResNet-50 model, trained on a large paediatric chest X-rays dataset, achieves high classification accuracy (95.94%), AUC-ROC (98.91%), and Cohen's Kappa (0.913), accompanied by clinically meaningful visual explanations. Our findings demonstrate that high performance and interpretability are not only achievable but critical for clinical AI deployment.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。